© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-1.7B
    5. 26-LLAMASCOPE-2-LORSA-16K-K64
    7. 1024
    Prev
    Next
    INDEX
    Explanations

    say fiber

    unknown · unknown
    New Auto-Interp
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Java
    -15.94
    Java
    -15.63
     England
    -15.63
    网络游戏
    -15.44
    England
    -15.44
     drugs
    -15.06
     JPEG
    -14.81
    UCT
    -14.38
    java
    -14.13
    Calcul
    -14.13
    POSITIVE LOGITS
    纤维
    21.63
    园
    21.25
     fiber
    17.88
    fib
    17.75
    经贸
    17.50
    饼
    17.00
     fibre
    16.88
    пед
    16.88
     ui
    16.88
    fiber
    16.63
    Activations Density 0.283%

    No Known Activations